seaweedfs/test/kafka/kafka-client-loadtest/docker-compose.yml

# SeaweedFS Kafka Client Load Test
# Tests the full stack: Kafka Clients -> SeaweedFS Kafka Gateway -> SeaweedFS MQ Broker -> Storage

x-seaweedfs-build: &seaweedfs-build
  build:
    context: .
    dockerfile: Dockerfile.seaweedfs
    args:
      TARGETARCH: ${GOARCH:-arm64}
      CACHE_BUST: ${CACHE_BUST:-latest}
  image: kafka-client-loadtest-seaweedfs

services:
  # Schema Registry (for Avro/Protobuf support) 
  # Using host networking to connect to localhost:9093 (where our gateway advertises)
  # WORKAROUND: Schema Registry hangs on empty _schemas topic during bootstrap
  # Pre-create the topic first to avoid "wait to catch up" hang
  schema-registry-init:
    image: confluentinc/cp-kafka:8.0.0
    container_name: loadtest-schema-registry-init
    networks:
      - kafka-loadtest-net
    depends_on:
      kafka-gateway:
        condition: service_healthy
    command: >
      bash -c "
      echo 'Creating _schemas topic...';
      kafka-topics --create --topic _schemas --partitions 1 --replication-factor 1 --bootstrap-server kafka-gateway:9093 --if-not-exists || exit 0;
      echo '_schemas topic created successfully';
      "
  
  schema-registry:
    image: confluentinc/cp-schema-registry:8.0.0
    container_name: loadtest-schema-registry
    restart: on-failure:3
    ports:
      - "8081:8081"
    environment:
      SCHEMA_REGISTRY_HOST_NAME: schema-registry
      SCHEMA_REGISTRY_HOST_PORT: 8081
      SCHEMA_REGISTRY_KAFKASTORE_BOOTSTRAP_SERVERS: 'kafka-gateway:9093'
      SCHEMA_REGISTRY_LISTENERS: http://0.0.0.0:8081
      SCHEMA_REGISTRY_KAFKASTORE_TOPIC: _schemas
      SCHEMA_REGISTRY_DEBUG: "true"
      SCHEMA_REGISTRY_SCHEMA_COMPATIBILITY_LEVEL: "full"
      SCHEMA_REGISTRY_LEADER_ELIGIBILITY: "true"
      SCHEMA_REGISTRY_MODE: "READWRITE"
      SCHEMA_REGISTRY_GROUP_ID: "schema-registry"
      SCHEMA_REGISTRY_KAFKASTORE_GROUP_ID: "schema-registry"
      SCHEMA_REGISTRY_KAFKASTORE_SECURITY_PROTOCOL: "PLAINTEXT"
      SCHEMA_REGISTRY_KAFKASTORE_TOPIC_REPLICATION_FACTOR: "1"
      SCHEMA_REGISTRY_KAFKASTORE_INIT_TIMEOUT: "120000"
      SCHEMA_REGISTRY_KAFKASTORE_TIMEOUT: "60000"
      SCHEMA_REGISTRY_REQUEST_TIMEOUT_MS: "60000"
      SCHEMA_REGISTRY_RETRY_BACKOFF_MS: "1000"
      # Force IPv4 to work around Java IPv6 issues
      # Enable verbose logging and set reasonable memory limits
      KAFKA_OPTS: "-Djava.net.preferIPv4Stack=true -Djava.net.preferIPv4Addresses=true -Xmx512M -Xms256M"
      KAFKA_LOG4J_OPTS: "-Dlog4j.configuration=file:/etc/kafka/log4j.properties"
      SCHEMA_REGISTRY_LOG4J_ROOT_LOGLEVEL: "INFO"
      SCHEMA_REGISTRY_KAFKASTORE_WRITE_TIMEOUT_MS: "60000"
      SCHEMA_REGISTRY_KAFKASTORE_INIT_RETRY_BACKOFF_MS: "5000"
      SCHEMA_REGISTRY_KAFKASTORE_CONSUMER_AUTO_OFFSET_RESET: "earliest"
      # Enable debug logging for Kafka clients to trace consumer seek/fetch operations
      SCHEMA_REGISTRY_LOG4J_LOGGERS: "org.apache.kafka.clients=DEBUG,org.apache.kafka.common=DEBUG,io.confluent.kafka.schemaregistry.storage=DEBUG"
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:8081/subjects"]
      interval: 15s
      timeout: 10s
      retries: 10
      start_period: 30s
    depends_on:
      schema-registry-init:
        condition: service_completed_successfully
      kafka-gateway:
        condition: service_healthy
    networks:
      - kafka-loadtest-net

  # SeaweedFS Master (coordinator)
  seaweedfs-master:
    <<: *seaweedfs-build
    container_name: loadtest-seaweedfs-master
    ports:
      - "9333:9333"
      - "19333:19333"
    command: 
      - master
      - -ip=seaweedfs-master
      - -port=9333
      - -port.grpc=19333
      - -volumeSizeLimitMB=48
      - -defaultReplication=000
      - -garbageThreshold=0.3
    volumes:
      - ./data/seaweedfs-master:/data
    healthcheck:
      test: ["CMD-SHELL", "wget --quiet --tries=1 --spider http://seaweedfs-master:9333/cluster/status || exit 1"]
      interval: 10s
      timeout: 5s
      retries: 10
      start_period: 20s
    networks:
      - kafka-loadtest-net

  # SeaweedFS Volume Server (storage)
  seaweedfs-volume:
    <<: *seaweedfs-build
    container_name: loadtest-seaweedfs-volume
    ports:
      - "8080:8080"
      - "18080:18080"
    command:
      - volume
      - -mserver=seaweedfs-master:9333
      - -ip=seaweedfs-volume
      - -port=8080
      - -port.grpc=18080
      - -publicUrl=seaweedfs-volume:8080
      - -preStopSeconds=1
      - -compactionMBps=50
      - -max=0
      - -dir=/data
    depends_on:
      seaweedfs-master:
        condition: service_healthy
    volumes:
      - ./data/seaweedfs-volume:/data
    healthcheck:
      test: ["CMD", "wget", "--quiet", "--tries=1", "--spider", "http://seaweedfs-volume:8080/status"]
      interval: 10s
      timeout: 5s
      retries: 5
      start_period: 15s
    networks:
      - kafka-loadtest-net

  # SeaweedFS Filer (metadata)
  seaweedfs-filer:
    <<: *seaweedfs-build
    container_name: loadtest-seaweedfs-filer
    ports:
      - "8888:8888"
      - "18888:18888"
      - "18889:18889"
    command:
      - filer
      - -master=seaweedfs-master:9333
      - -ip=seaweedfs-filer
      - -port=8888
      - -port.grpc=18888
      - -metricsPort=18889
      - -defaultReplicaPlacement=000
    depends_on:
      seaweedfs-master:
        condition: service_healthy
      seaweedfs-volume:
        condition: service_healthy
    volumes:
      - ./data/seaweedfs-filer:/data
    healthcheck:
      test: ["CMD", "wget", "--quiet", "--tries=1", "--spider", "http://seaweedfs-filer:8888/"]
      interval: 10s
      timeout: 5s
      retries: 5
      start_period: 15s
    networks:
      - kafka-loadtest-net

  # SeaweedFS MQ Broker (message handling)
  seaweedfs-mq-broker:
    <<: *seaweedfs-build
    container_name: loadtest-seaweedfs-mq-broker
    ports:
      - "17777:17777"
      - "18777:18777"  # pprof profiling port
    command:
      - mq.broker
      - -master=seaweedfs-master:9333
      - -ip=seaweedfs-mq-broker
      - -port=17777
      - -logFlushInterval=0
      - -port.pprof=18777
    depends_on:
      seaweedfs-filer:
        condition: service_healthy
    volumes:
      - ./data/seaweedfs-mq:/data
    healthcheck:
      test: ["CMD", "nc", "-z", "localhost", "17777"]
      interval: 10s
      timeout: 5s
      retries: 5
      start_period: 20s
    networks:
      - kafka-loadtest-net

  # SeaweedFS Kafka Gateway (Kafka protocol compatibility)
  kafka-gateway:
    <<: *seaweedfs-build
    container_name: loadtest-kafka-gateway
    ports:
      - "9093:9093"
      - "10093:10093"  # pprof profiling port
    command:
      - mq.kafka.gateway
      - -master=seaweedfs-master:9333
      - -ip=kafka-gateway
      - -ip.bind=0.0.0.0
      - -port=9093
      - -default-partitions=4
      - -schema-registry-url=http://schema-registry:8081
      - -port.pprof=10093
    depends_on:
      seaweedfs-filer:
        condition: service_healthy
      seaweedfs-mq-broker:
        condition: service_healthy
    environment:
      - SEAWEEDFS_MASTERS=seaweedfs-master:9333
      # - KAFKA_DEBUG=1  # Enable debug logging for Schema Registry troubleshooting
      - KAFKA_ADVERTISED_HOST=kafka-gateway
    volumes:
      - ./data/kafka-gateway:/data
    healthcheck:
      test: ["CMD", "nc", "-z", "localhost", "9093"]
      interval: 10s
      timeout: 5s
      retries: 10
      start_period: 45s  # Increased to account for 10s startup delay + filer discovery
    networks:
      - kafka-loadtest-net

  # Kafka Client Load Test Runner
  kafka-client-loadtest:
    build:
      context: ../../..
      dockerfile: test/kafka/kafka-client-loadtest/Dockerfile.loadtest
    container_name: kafka-client-loadtest-runner
    depends_on:
      kafka-gateway:
        condition: service_healthy
      # schema-registry:
      #   condition: service_healthy
    environment:
      - KAFKA_BOOTSTRAP_SERVERS=kafka-gateway:9093
      - SCHEMA_REGISTRY_URL=http://schema-registry:8081
      - TEST_DURATION=${TEST_DURATION:-300s}
      - PRODUCER_COUNT=${PRODUCER_COUNT:-10}
      - CONSUMER_COUNT=${CONSUMER_COUNT:-5}
      - MESSAGE_RATE=${MESSAGE_RATE:-1000}
      - MESSAGE_SIZE=${MESSAGE_SIZE:-1024}
      - TOPIC_COUNT=${TOPIC_COUNT:-5}
      - PARTITIONS_PER_TOPIC=${PARTITIONS_PER_TOPIC:-3}
      - TEST_MODE=${TEST_MODE:-comprehensive}
      - SCHEMAS_ENABLED=${SCHEMAS_ENABLED:-true}
      - VALUE_TYPE=${VALUE_TYPE:-avro}
    profiles:
      - loadtest
    volumes:
      - ./test-results:/test-results
    networks:
      - kafka-loadtest-net

  # Monitoring and Metrics
  prometheus:
    image: prom/prometheus:latest
    container_name: loadtest-prometheus
    ports:
      - "9090:9090"
    volumes:
      - ./monitoring/prometheus.yml:/etc/prometheus/prometheus.yml
      - prometheus-data:/prometheus
    networks:
      - kafka-loadtest-net
    profiles:
      - monitoring

  grafana:
    image: grafana/grafana:latest
    container_name: loadtest-grafana
    ports:
      - "3000:3000"
    environment:
      - GF_SECURITY_ADMIN_PASSWORD=admin
    volumes:
      - ./monitoring/grafana/dashboards:/var/lib/grafana/dashboards
      - ./monitoring/grafana/provisioning:/etc/grafana/provisioning
      - grafana-data:/var/lib/grafana
    networks:
      - kafka-loadtest-net
    profiles:
      - monitoring

  # Schema Registry Debug Runner
  schema-registry-debug:
    build:
      context: debug-client
      dockerfile: Dockerfile
    container_name: schema-registry-debug-runner
    depends_on:
      kafka-gateway:
        condition: service_healthy
    networks:
      - kafka-loadtest-net
    profiles:
      - debug

volumes:
  prometheus-data:
  grafana-data:

networks:
  kafka-loadtest-net:
    driver: bridge
    name: kafka-client-loadtest